Instructions to use rbelanec/train_openbookqa_101112_1760638025 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_openbookqa_101112_1760638025 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
model = PeftModel.from_pretrained(base_model, "rbelanec/train_openbookqa_101112_1760638025")

Transformers

How to use rbelanec/train_openbookqa_101112_1760638025 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="rbelanec/train_openbookqa_101112_1760638025")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rbelanec/train_openbookqa_101112_1760638025", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rbelanec/train_openbookqa_101112_1760638025 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rbelanec/train_openbookqa_101112_1760638025"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rbelanec/train_openbookqa_101112_1760638025",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_openbookqa_101112_1760638025

SGLang

How to use rbelanec/train_openbookqa_101112_1760638025 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "rbelanec/train_openbookqa_101112_1760638025" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rbelanec/train_openbookqa_101112_1760638025",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "rbelanec/train_openbookqa_101112_1760638025" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rbelanec/train_openbookqa_101112_1760638025",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_openbookqa_101112_1760638025 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_openbookqa_101112_1760638025
```

train_openbookqa_101112_1760638025

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the openbookqa dataset. It achieves the following results on the evaluation set:

Loss: 0.5690
Num Input Tokens Seen: 8474968

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.03
train_batch_size: 4
eval_batch_size: 4
seed: 101112
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Input Tokens Seen
0.6942	1.0	1116	0.6966	424568
0.6806	2.0	2232	0.7041	848552
0.691	3.0	3348	0.6953	1271776
0.6917	4.0	4464	0.6958	1694896
0.7066	5.0	5580	0.6869	2118456
0.6931	6.0	6696	0.6998	2542752
0.6141	7.0	7812	0.6466	2966512
0.4988	8.0	8928	0.6209	3390048
0.5554	9.0	10044	0.5843	3814704
0.4766	10.0	11160	0.5740	4238440
0.4587	11.0	12276	0.5826	4662136
0.6224	12.0	13392	0.5690	5086336
0.393	13.0	14508	0.5838	5510768
0.4478	14.0	15624	0.5707	5933936
0.3398	15.0	16740	0.5972	6357536
0.3969	16.0	17856	0.5900	6779872
0.1803	17.0	18972	0.6234	7203216
0.2085	18.0	20088	0.6647	7626944
0.2846	19.0	21204	0.6692	8051216
0.3797	20.0	22320	0.6721	8474968

Framework versions

PEFT 0.17.1
Transformers 4.51.3
Pytorch 2.9.0+cu128
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: -

Model tree for rbelanec/train_openbookqa_101112_1760638025

Base model

meta-llama/Meta-Llama-3-8B-Instruct

Adapter

(2405)

this model